Selected talks

• On multi-armed bandit algorithms for (early stage) clinical trials. Conference on Statistics and Biopharmacy (SNB), Paris. September 2022.
• Two classes on bandits at the EURO summer school. Frequentist bandits. Bayesian bandits. July 2022.
• Non parametric exploration in multi-armed bandit models. Plenary speaker at the Journées de Statistiques, Lyon. June 2022.
• On pure exploration in (episodic) Markov Decision Processes. Workshop on RL Theory @ICML 2021.
• On the complexity of learning good policies with and without rewards. University of Alberta (virtual) seminar. November 2020.
• On the complexity of learning good policies with and without rewards. Invited talk at the Simmons institute, in the Mathematics of Online Decision Making (virtual) workshop. October 2020.
• Practical Algorithms for Multi-Player Bandits. Invited talk at the Allerton Conference. University of Illinois, USA. September 2019.
• Practical Algorithms for Multi-Player Bandits. MAPLE workshop (Markets, Algorithms, Prediction and Learning), Milan, Italy. September 2019.
• Conference Plénière au GRETSI 2019, Lille, France. Quelques outils statistiques pour la prise de décision séquentielle. August 2019.
• Reinforcement Learning Summer School in Lille, July 2019.
• Stastics seminar, University of Leiden, May 2019. Generalized Likelihood Ratios Tests applied to Sequential Decision Making.
• AAAI workshop on Reinforcement Learning for Games, Honolulu, January 2019. Beyond Classical Bandit Tools for Monte-Carlo Tree Search.
• Paris Symposium on Game Theory, Paris, June 2018. Bandit (for) Games.
• Workshop on Modern Challenges for Learning Theory, Université de Montréal, April 2018. Bandits (for) Games.
• Tech talk at Amazon, Berlin, March 2018. Bandits (for) Games.
• Imaging Seminar, Paris, November 2017. A tutorial on Multi-Armed Bandit problems: Theory and Practice.
• Inria-CWI workshop, Amsterdam, September 2017. Monte-Carlo Tree Search by Best Arm Identification.
• Joint tutorial on bandits for cognitive radio with Christophe Moy at the International Conference on Communication (ICC), Paris May 2017. Online learning for real-time dynamic spectrum access: from theory to practice.
• Popularization talk in French at the Mathematik Park seminar, Paris April 2017. Outils et modèles statistiques pour l'allocation séquentielle de ressources.
• Workshop on Optimization and Decision-Making Under Uncertainty, Simons Institute, Berkeley, September 2016. Revising the Exploration-Exploitation tradeoff in Bandit Models.
• Journées MAS 2016, Grenoble , August 2016. Stratégies bayésiennes et fréquentistes dans un modèle de bandit.
• GDR ISIS, Paris, June 2016.A novel spectral algorithm for the identification of overlapping communities in networks.
• SMF 2016: 1er Congrès de la Société Mathématique de France, Tours, June 2016.
• GDR ISIS, Paris, June 2016. Two examples of discrete PAC optimization.
• Statslab Seminar, University of Cambridge, April 2016.
• RecSys FR Meetup, Rakuten Group, March 2016. New tools from the bandit literature to improve A/B Testing
• Workshop on Computational and Statistical Trade-offs in Learning , IHES, March 2016. Optimal Best Arm Identification with Fixed Confidence
• Seminar of the Collegio Carlo Alberto, Torino, March 2016.
• Stor-i Multi-armed bandit workshop, Lancaster, January 2016. The information complexity of best-arm identification
• SIGMA seminar, Ecole Centrale de Lille, November 2015. On Bayesian algorithms for sequential resource allocation.
• Workshop on Sequential Learning and Applications, Toulouse, November 2015. On Bayesian index policies for sequential resource allocation.
• UW/MSR Workshop, Seattle, August 2015. On Bayesian index policies for sequential resource allocation.
• LINCS Seminar, Paris, June 2015.An adaptive spectral algorithm for the recovery of overlapping communities in networks.
• SMILE Seminar, Paris, June 2015.The information complexity of sequential resource allocation.
• Machine Learning Seminar, ENS Cachan, May 2015.
• Séminaire de l'équipe SAMM, Université Paris 1, March 2015.
• Séminaire de statistique appliquée, Université de Strasbourg, March 2015.
• Séminaire de probabilistés et statistiques du Laboratoire Paul Painlevé, Lille, February 2015.
• Journées YSP, IHP, January 2015. Une introduction à l'allocation séquentielle de ressources (tutorial in French).
• INRIA TAO Seminar, Saclay, January 2015.
• Séminaire de Statistiques et Imagerie, Université Paris-Dauphine, December 2014.
• INRIA SIERRA Seminar, Paris, December 2014.
• Paris Game Theory Seminar, Institut Henri Poincaré, November 2014.
• Probability and statistics seminar, Université d'Angers, October 2014. (slides)
• Junior Seminar, INRIA, October 2014. Optimal algorithms for sequential resource allocation.
• Journées MAS, Toulouse, August 2014. Two optimization problems in a stochastic bandit model.
• Statistics seminar of Université Paris Sud, Orsay, May 2014. Bayesian and Frequentist Methods in Bandit Models.
• Bayes In Paris seminar, ENSAE, October 2013. (slides)
• 5èmes Rencontres des Jeunes Statisticiens, Aussois, August 2013. (slides)
• Wilks Seminar, Princeton University, May 2013. Bayesian and Frequentist methods for bandit models .
• SMILE Seminar, November 2012. Un point de vue bayésien pour des algorithmes de bandit plus performants .
• Workshop 'New Chalenges in Exploration and Exploitation', ICML 2012. On Bayesian bandit algorithms.